[alm1]

I think the deterministic requirement was what made the semantic web nearly impossible at scale. Aligning on the schema for all the entities can be challenging within a small group, yet alone the world. Doing it continuously is impossible today. Wikidata has tons of abandoned and branches which are no longer relevant or even wrong.

It seems like LLMs and vector representations for words are more practical ways to explore semantic data. Then the specific, reccuring queries may be optimized through graph representations.

[potatolicious]

A good way to think about it is that the "semantic web" was all about finding some kind of universal data representation for the world's data, and that has failed in large part because data representation is inherently application-specific.

The only practicable version of the semantic web needs to embrace that reality. We need tools for converting, extracting, and interpreting data from one application-specific data representation to another.

Sometimes that's LLMs, sometimes it can be done heuristically, but either way, the notion of the universal data structure simply isn't realistic.